Training method of gang recognition model and abnormal gang recognition method and device
A technology of identification model and training method, applied in the field of training of gang identification model, can solve the problems of inaccurate identification results of abnormal gangs, failure to consider gang dimension feature data, etc., and achieve the effect of reducing the feature search space and time complexity.
Active Publication Date: 2021-08-20
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, most of the characteristic data used in the current training of gang identification models are based on the dimension of individual members, without considering the characteristic data of the gang dimension, resulting in inaccurate identification results of the trained model for abnormal gangs
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0060] In order to make the purpose, technical solution and advantages of this specification clearer, the technical solution of this specification will be clearly and completely described below in conjunction with specific embodiments of this specification and corresponding drawings. Apparently, the described embodiments are only some of the embodiments in this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of this document.
[0061] As mentioned above, the traditional abnormal group identification scheme uses the characteristic data of individual members to train the model, and does not consider the characteristic data of the group dimension, resulting in the inability to accurately identify abnormal groups using the trained model.
[0062] To this end, the embodiment of this specification aims to provide a sch...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The embodiment of the invention discloses a gang recognition model training method, an abnormal gang recognition method and an abnormal gang recognition device. The gang recognition model training method comprises the steps that service feature data of a user in a sample gang, a corresponding individual tag and a gang tag corresponding to the sample gang are collected, the individual tag is used for indicating whether the user has risks or not, and the gang tag is used for indicating whether the sample gang is abnormal or not; establishing a random forest model based on the service feature data of the users in the sample gang and the individual tags corresponding to the users; determining a plurality of target feature groups with maximum information gain parameters based on nodes on a plurality of decision trees contained in the random forest model and information gain parameters when service features represented by the nodes are split by different split values; based on the plurality of target feature groups, aggregating the service feature data of the users in the sample gang to obtain gang features of the sample gang; and training a gang recognition model based on the gang features of the sample gang and the corresponding gang labels.
Description
technical field [0001] This document relates to the field of artificial intelligence technology, in particular to a training method for a gang recognition model, a method and a device for identifying abnormal gangs. Background technique [0002] In risk control scenarios such as embezzlement and cheating, gangs usually commit crimes, and gang members colluding with each other can easily cause serious asset losses. With the development of artificial intelligence, more and more institutions adopt machine learning models to identify abnormal gangs. However, most of the characteristic data used in the current training of gang identification models are based on the dimension of individual members, without considering the characteristic data of the gang dimension, resulting in inaccurate identification results of the trained model for abnormal gangs. [0003] In view of this, there is an urgent need for a solution that can accurately identify abnormal groups. Contents of the in...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06Q50/26G06Q10/06G06K9/62
CPCG06Q50/26G06Q10/0635G06F18/24323G06F18/214
Inventor 张丽娟
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD